Systematic Testing of Convolutional Neural Networks for Autonomous Driving

Abstract

We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles. Our analysis procedure comprises an image generator that produces synthetic pictures by sampling in a lower dimension image modification subspace and a suite of visualization tools. The image generator produces images which can be used to test the CNN and hence expose its vulnerabilities. The presented framework can be used to extract insights of the CNN classifier, compare across classification models, or generate training and validation datasets.

References in corpus (1)

• End to End Learning for Self-Driving Cars

Cited by in corpus (10)

• Testing Deep Neural Networks
• Machine Learning Testing: Survey, Landscapes and Horizons
• Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
• How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
• Towards Verified Artificial Intelligence
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
• A Formalization of Robustness for Deep Neural Networks
• Rapidly-exploring Random Trees-based Test Generation for Autonomous Vehicles
• Can Offline Testing of Deep Neural Networks Replace Their Online Testing?